My function calls are no longer working when I select gpt-40-mini. They will only work with gpt-40-cluster.

It sounds like you're having some trouble with function calls when using the gpt-40-mini model. Here are a few troubleshooting steps you can try to resolve the issue: 1. **Check Function and Tool Configuration**: Make sure that the necessary tools like

transferCall

,

endCall

, and

dtmf

are included in your assistant's tools list. You need to explicitly add these tools to your model's

tools

array. 2. **Verify System Configuration and Logs**: Ensure that the function descriptions are properly defined and check the Vapi logs for any errors that might indicate where the problem is occurring. 3. **Validate Server URL and Endpoint Configuration**: Confirm that your server URL is correctly set up at the account level or within the assistant's configuration. Make sure the local server is running and handling requests correctly. 4. **Test Functionality Thoroughly**: Conduct thorough testing of the call forwarding and other automated actions to confirm their functionality. Set up scenarios that mimic real-world uses to identify any misconfigurations. If these steps don't resolve the issue, it might be helpful to review the [Vapi documentation](https://docs.vapi.ai/) for more detailed guidance or check for any updates regarding the gpt-40-mini model. Let me know if you need further assistance! 😊 Sources: - [Function Calling in Vapi](https://docs.vapi.ai/assistants/function-calling) - [Setting Server URLs](https://docs.vapi.ai/server-url/setting-server-urls) - [Vapi Documentation](https://docs.vapi.ai/)

All is setup correctly. It only works when I switch to gpt-40-cluster.

Hey! To help track down this issue, could you share: - The call ID - What response you expected to get - What response you actually got instead This would really help us figure out what went wrong!